|
| 超像素级局部对比的声图水下小目标检测方法 |
| Superpixel-level local contrast method for underwater small target detection in sonar images |
| 投稿时间：2024-09-25 修订日期：2024-12-27 |
| 中文摘要: |
| 针对声纳图像信噪比低和样本少等引起的水下小目标检测率低和虚警高的问题，提出了一种超像素级局部对比的水下小目标检测方法。该方法利用了简单线性迭代聚类算法，将相似强度的相邻像素自适应分组，构造超像素声图；利用声图增强和分割方法，通过局部超像素分组、剔除平均统计和浓度比局部对比增强等处理，有针对性地增强目标，抑制复杂背景，进而提高目标检测率；结合声图信噪比、浓度及功率等统计参数，对声图感兴趣区域进行统计评估和筛选，降低虚警率。经过真实声纳图像验证，该方法能够有效提高小目标检测率和降低虚警率，尤其适用于样本少和信噪比低的水下小目标检测。 |
| 英文摘要: |
| A superpixel-level local contrast method of underwater small target detection is proposed to address the problems of low detection rate and high false alarms caused by low signal-to-noise ratio and few samples in sonar images. This method uses the simple linear iterative clustering algorithm that adaptively groups neighboring pixels with similar intensity to construct superpixel sonar images; using the method of sonar image enhancement and segmentation, the true target is enhanced purposefully and the complex background is suppressed by local superpixel grouping, eliminating average statistics and concentration ratio local contrast enhancement, to improve the target detection rate; combined with the statistical parameters of signal-to-noise ratio, concentration and power of the sonar image, the statistical evaluation and screening of the region of interest of the sonar images is carried out to reduce the false alarm rate. Experiments performed on real sonar images demonstrate this method can effectively improve the detection rate of small targets and reduce false alarm rates, especially suitable for underwater target detection with few samples and low signal-to-noise ratio. |
| DOI： |
| 中文关键词: 水下小目标检测 声纳图像 局部对比度 超像素级 |
| 英文关键词: Underwater small target detection Sonar images Local contrast Superpixel level |
| 基金项目: |
|
| 摘要点击次数: 4 |
| 全文下载次数: 0 |
|
查看/发表评论 下载PDF阅读器 |
| 关闭 |
